Dataviz mit Plotly PL Data

Fragestellung: “Die Manschafft, die zur Halbzeit vorne liegt, gewinnt mit einer Chance von mindestens 75% auch das Spiel. Falls zur Halbzeit unentschieden ist, gewinnt eher das Heimteam (Chance > 33.4%).”

Dafür nehmen wir den Datacamp Datensatz Soccer Data

Als Einführung werden wir auf Datacamp folgende Kurse durchgehen:

• Interactive Data Visualization with plotly

• Intermediate Interactive Data Visualization with plotly

# Bibliotheken importieren
library("plotly")
library("plyr")
library("dplyr")
library("forcats")
library("RColorBrewer")

Daten einlesen und Dataframe erstellen

# List files in folder "Data"
files <- list.files(path="./Data/", pattern=NULL, all.files=FALSE, full.names=TRUE)

# Create Dataframe with all csv from years 2015-2019
df <- ldply(.data = files, .fun = read.csv)

View(df)

# Count frequency of haltime & fulltime results
df_htr <- df %>% count(HTR)
df_ftr <- df %>% count(FTR)

# Create dataframe with halttime & fulltime result amounts
df_results <- data.frame(c("Away", "Draw", "Home"), c(df_htr$n), c(df_ftr$n))

# Rename column headers
col_headings <- c('Result','Halftime','Fulltime')
names(df_results) <- col_headings

# Plot grouped bar chart to visualize halftime & fulltime results
fig <- plot_ly(
  df_results, x = ~Results, y = ~Halftime, type = 'bar', name = 'Half Time Score') %>% 
  add_trace(y = ~Fulltime, name = 'Full Time Score') %>%
  layout(yaxis = list(title = 'Count'), barmode = 'group')

fig

# merge HTR & FTR to 1 column
df$result <- paste(df$HTR, df$FTR)

print("Example: H H = home team is winning at halftime and also wins the game at fulltime")

[1] "Example: H H = home team is winning at halftime and also wins the game at fulltime"

# Plot all different game progresses and their amount
df %>%
  count(result) %>%
  mutate(result = fct_reorder(result, n, .desc = TRUE)) %>%
  plot_ly(x = ~result, y = ~n, text = ~n, textposition = 'auto') %>%
  add_bars() %>%
  layout(xaxis = list(title = "Game Progress"),
         yaxis = list(title = "Amount"),
         title = "How are the different game progresses distributed?")

# Group by game outcome & calculate probability of all outcomes
df_count_results <- df %>% 
  group_by(result) %>% 
  summarise(count_result = round(n() / nrow(df) * 100, digits = 2))

df_count_results %>%
  plot_ly(labels = ~result, values = ~count_result) %>%
  add_pie(hole = 0.4, color = I("white")) %>%
  layout(xaxis = list(title = "Game Progress"),
         yaxis = list(title = "Probability %"),
         title = "What is the probability of each game progress?")

# Calculate probability 
calc_prob <- function(df1, df2) {
  prob <- round((100 / nrow(df1) * nrow(df2)), digits = 2)
  return(prob)
}

# Filter home teams winning at halftime
df_ht_home <- df %>% 
  filter(HTR == "H")

# Filter home teams winning at halftime & fulltime
df_ft_home <- df_ht_home %>% 
  filter(FTR == "H")

home_win_prob <- calc_prob(df_ht_home, df_ft_home)

cat("Probability that the home team wins the game if they are leading at half time: ", home_win_prob, "%")

Probability that the home team wins the game if they are leading at half time:  82.55 %

# Filter away teams winning at halftime
df_ht_away <- df %>% 
  filter(HTR == "A")

# Filter away teams winning at halftime & fulltime
df_ft_away <- df_ht_away %>% 
  filter(FTR == "A")

away_win_prob <- calc_prob(df_ht_away, df_ft_away)

cat("Probability that the away team wins the game if they are leading at half time: ", away_win_prob, "%")

Probability that the away team wins the game if they are leading at half time:  72.03 %

# Filter draw at halftime
df_ht_draw <- df %>% 
  filter(HTR == "D")

# Filter draw at halftime & fulltime
df_ft_draw <- df_ht_draw %>% 
  filter(FTR == "D")

draw_prob <- calc_prob(df_ht_draw, df_ft_draw)

cat("Probability that the game ends in a draw if the halftime result is also a draw: ", draw_prob, "%")

Probability that the game ends in a draw if the halftime result is also a draw:  36.45 %

# Filter draw at halftime & the home team winning at fulltime
df_ht_draw_ft_home_win <- df_ht_draw %>%
  filter(FTR == "H")

home_win_after_ht_draw_prob <- calc_prob(df_ht_draw, df_ht_draw_ft_home_win)

cat("Probability that the home team wins if the halftime result is a draw: ", home_win_after_ht_draw_prob, "%")

Probability that the home team wins if the halftime result is a draw:  38.03 %

# Probability that the team winning at half time wins the game
ht_ft_win_prob <- round(((home_win_prob * nrow(df_ft_home)) + (away_win_prob * nrow(df_ft_away))) / (nrow(df_ft_home) + nrow(df_ft_away)), digits = 2)

cat("Probability that the team leading at half time wins the entire game: ", ht_ft_win_prob, "%")

Probability that the team leading at half time wins the entire game:  78.41 %